The bias due to incomplete matching

Observational studies comparing groups of treated and control units are often used to estimate the effects caused by treatments. Matching is a method for sampling a large reservoir of potential controls to produce a control group of modest size that is ostensibly similar to the treated group. In practice, there is a trade-off between the desires to find matches for all treated units and to obtain matched treated-control pairs that are extremely similar to each other. We derive expressions for the bias in the average matched pair difference due to the failure to match all treated units--incomplete matching, and the failure to obtain exact matches--inexact matching. A practical example shows that the bias due to incomplete matching can be severe, and moreover, can be avoided entirely by using an appropriate multivariate nearest available matching algorithm, which, in the example, leaves only a small residual bias due to inexact matching.

Difficulties with regression analyses of age-adjusted rates

A common type of observational study compares population rates in several regions having differing policies in an effort to assess the effects of those policies. In many studies, particularly in public health and epidemiology, age-adjusted rates are regressed on predictor variables to give a covariance-adjusted estimate of effect; this estimate is shown to be generally biased for the appropriate regression coefficient. For familiar models, the analysis of crude rates with age as a covariate can lead to unbiased estimates, and therefore can be preferable. Several other regression methods are also considered.

Cisplatin, doxorubicin, cyclophosphamide, lomustine, and vincristine (PACCO) in the treatment of non-small cell bronchogenic carcinoma

A total of 43 patients with non-small cell carcinoma from a small preliminary trial and a larger in-house study were evaluated after treatment with cisplatin (50 mg/m2), doxorubicin (50 mg/m2), cyclophosphamide (300 mg/m2), and vincristine (1.4 mg/m2), all given iv on Day 1, and lomustine (50 mg/m2) given orally on Day 1. The response rate in the larger trial was 9%, with a 95% confidence interval of 2%-24%. For the combined group of all patients, median survival was 200 days, with a 95% confidence interval of 115-229 days. Hematologic toxicity and nausea and vomiting were moderate to severe and there were two treatment-related deaths. This combination drug regimen appears to have no advantages over other, less toxic regimens in the treatment of non-small cell bronchogenic carcinoma.

Aggressive combined modality therapy for advanced local-regional breast carcinoma

Thirty-two women with advanced local regional breast carcinoma, including nine patients with histologically diagnosed inflammatory cancer, were entered on a prospective pilot study. They were treated aggressively with initial surgery, two courses of induction chemotherapy with cyclophosphamide, methotrexate, 5-fluorouracil, +/- prednisone, +/- tamoxifen (CMF [P] [T]), local-regional radiotherapy, and then maintenance chemotherapy with CMF(P) (T) alternating with doxorubicin, vincristine, +/- tamoxifen (AV[T]). The patients have been followed for 19-70 months from the time of mastectomy and their actuarial three-year survival is 65% with a median survival that has not yet been reached. Median disease-free survival (time to progression) is currently 29.5 months. Women whose gross disease could not be totally resected surgically had shorter disease-free survivals than those rendered surgically free of disease (p = 0.01). Clinically evident cardiotoxicity was seen in 25% of the patients and was felt to be primarily due to the combination of doxorubicin and radiation therapy. It was significantly more common (Plt less than 0.05) in patients with left chest irradiation (seven of 18 women) as opposed to those with right-sided irradiation (one of 14).

Case definition and power in case-control studies

A narrow case definition can lead to greater in clarity in case-control studies, but it can also lead to either a gain or a loss in the power of statistical tests. Under plausible assumptions, the loss of power can be in excess of 30 per cent, and the gain can be in excess of 50 per cent. If at least one third of the total study size consists of narrowly defined cases, the loss of power will often be negligible, whereas the gain can be substantial.